{"slug": "gemini-4-carbon-high-scores-59-on-artificial-analysis-v5", "title": "Gemini 4 Carbon (High) Scores 59 on Artificial Analysis v5", "summary": "Google's Gemini 4 Carbon (High), released October 28, 2026, scored 59 on the Artificial Analysis Intelligence Index, well above the median of 42 for models in its price tier, according to Artificial Analysis. The reasoning model accepts text, image, speech and video input, outputs text, carries a 1M-token context window, and generated 200M tokens during the index evaluation versus a median of 64M. Google prices Gemini 4 Carbon (High) at $4.00 per 1M input tokens and $20.00 per 1M output tokens, against medians of $2.00 and $10.00, for an average cost of $7.76 per task on the Intelligence Index.", "body_md": "# Gemini 4 Carbon (High) Intelligence, Performance & Price Analysis\n\n### Model summary\n\n#### Speed\n\nGemini 4 Carbon (High) is amongst the leading models in intelligence, but somewhat expensive when comparing to other models of similar price. The model supports text, image, speech, and video input, outputs text, and has a 1M tokens context window.\n\nGemini 4 Carbon (High) scores 59 on the Artificial Analysis Intelligence Index, placing it well above average among comparable models (median: 42). When evaluating the Intelligence Index, it generated 200M tokens, which is very verbose in comparison to the median of 64M.\n\nPricing for Gemini 4 Carbon (High) is $4.00 per 1M input tokens (somewhat expensive, median: $2.00) and $20.00 per 1M output tokens (expensive, median: $10.00). On average, it costs $7.76 per task to evaluate Gemini 4 Carbon (High) on the Intelligence Index.\n\n| Reasoning | Yes This page shows the reasoning version of this model. A non-reasoning variant may also exist. | \n|---|---|\n| Input modality | Supports: text, image, speech, and video | \n| Output modality | Supports: text | \n| Context window | 1M ~1500 A4 pages of size 12 Arial font | \n\nMetrics are compared against models of the same class:\n\n- Non-reasoning models → compared only with other non-reasoning models\n- Reasoning models → compared across both reasoning and non-reasoning\n- Open weights models → compared only with other open weights models of the same size class:\n- Tiny: ≤4B parameters\n- Small: 4B–40B parameters\n- Medium: 40B–150B parameters\n- Large: >150B parameters\n- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:\n- <$0.15 per 1M tokens\n- $0.15–$1 per 1M tokens\n- >$1 per 1M tokens\n\n### Speed\n\n## Intelligence\n\n### [Artificial Analysis Intelligence Index](https://artificialanalysis.ai/evaluations/artificial-analysis-intelligence-index)\n\n### Artificial Analysis Intelligence Index by Open Weights / Proprietary\n\n### Intelligence Index vs. Cost per Task\n\nMeasures the performance of models on specific capabilities and industries\n\n### [Artificial Analysis Finance & Accounting Index](https://artificialanalysis.ai/indexes/finance-and-accounting)\n\n### Evaluations\n\nAgentic knowledge work, Elo\n\nKnowledge\n\n1 - hallucination rate\n\nAgentic SaaS workflows\n\nAgentic scientific research workflows in a terminal\n\nAgentic software engineering in open-source repositories\n\nReasoning & knowledge\n\nProfessional document reasoning, All-pass\n\nAgentic coding & terminal use\n\nPhysics reasoning\n\nQuantitative analysis on spreadsheets & documents\n\nLegal agentic work, Hallucination-Gated All-Pass Rate\n\nAgentic business operations\n\nAgentic real-world work tasks, Elo\n\nAgentic interactive 3D experiences, Elo\n\nProduct and brand videos designed in code, Elo\n\nKubernetes incident root-cause analysis\n\nMedical long context reasoning\n\nVisual reasoning\n\nRich, varied, well-crafted language\n\nWell-structured, scannable, answer-first\n\nTruthful, acknowledges uncertainty, non-sycophantic\n\nUse of filler and generic language\n\n### AA-Briefcase v1.1\n\n### AA-Briefcase Elo\n\n### AA-Omniscience v1.1\n\n### AA-Omniscience Index\n\n## Intelligence Index Comparisons\n\n### Intelligence Index vs. Cost per Task\n\n## Token Use\n\n### Output Tokens per Intelligence Index Task\n\n## Cost\n\n### Cost per Intelligence Index Task\n\n### Cost to Run Artificial Analysis Intelligence Index\n\n### Pricing: Cache Hit, Input, and Output\n\n## Context Window\n\n### Context Window\n\n## Frequently Asked Questions\n\nCommon questions about Gemini 4 Carbon (High)\n\nGemini 4 Carbon (High) was released on October 28, 2026.\n\nGemini 4 Carbon (High) was created by Google.\n\nGemini 4 Carbon (High) scores 59 on the Artificial Analysis Intelligence Index, placing it well above average among other models in a similar price tier (median: 42).\n\nGemini 4 Carbon (High) costs $4.00 per 1M input tokens (somewhat higher than average, median: $2.00) and $20.00 per 1M output tokens (at the higher end, median: $10.00), based on Google's API.\n\nGemini 4 Carbon (High) costs $4.00 per 1M input tokens and $20.00 per 1M output tokens (based on Google's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $2.94 per 1M tokens. Pricing may vary by provider. [Compare provider pricing](https://artificialanalysis.ai/models/gemini-4-carbon/providers)\n\nWhen evaluated on the Intelligence Index, Gemini 4 Carbon (High) generated 200M output tokens, which is at the higher end compared to other models in a similar price tier (median: 64M).\n\nYes, Gemini 4 Carbon (High) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.\n\nGemini 4 Carbon (High) supports text, image, speech, and video input.\n\nGemini 4 Carbon (High) supports text output.\n\nYes, Gemini 4 Carbon (High) supports image input and can analyze, describe, and answer questions about images.\n\nYes, Gemini 4 Carbon (High) is multimodal. It can process text, image, speech, and video input and generate text output.\n\nGemini 4 Carbon (High) has a context window of 1.0M tokens. This determines how much text and conversation history the model can process in a single request.\n\nNo, Gemini 4 Carbon (High) is proprietary. The model weights are not publicly available.\n\nGemini 4 Carbon (High) is a proprietary model and Google has not disclosed the model size or parameter count.\n\nGemini 4 Carbon (High) achieves a score of 59 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.\n\nYes, Gemini 4 Carbon (High) is available via API through 1 provider. [Compare API providers](https://artificialanalysis.ai/models/gemini-4-carbon/providers)\n\nGemini 4 Carbon (High) is available through 1 API provider. [Compare providers](https://artificialanalysis.ai/models/gemini-4-carbon/providers)", "url": "https://wpnews.pro/news/gemini-4-carbon-high-scores-59-on-artificial-analysis-v5", "canonical_source": "https://artificialanalysis.ai/models/gemini-4-carbon", "published_at": "2026-10-28 17:23:42+00:00", "updated_at": "2026-10-28 17:42:27.374133+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research"], "entities": ["Google", "Gemini 4 Carbon (High)", "Artificial Analysis", "Artificial Analysis Intelligence Index"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/gemini-4-carbon-high-scores-59-on-artificial-analysis-v5", "markdown": "https://wpnews.pro/news/gemini-4-carbon-high-scores-59-on-artificial-analysis-v5.md", "text": "https://wpnews.pro/news/gemini-4-carbon-high-scores-59-on-artificial-analysis-v5.txt", "jsonld": "https://wpnews.pro/news/gemini-4-carbon-high-scores-59-on-artificial-analysis-v5.jsonld"}}